전체 검색

AI 모델 450

• Rocinante-X-12B-v1-GGUF↗

  TheDrummer

  Hi! I'm Drummer. I'm a Software Engineer with experience in JavaScript, Golang, Python, and generally engineering the crap out of things. - **Exploration:** Everyone is trying to figure out how AI works and what it's capable of. I am too - just not in creating the smartest, safest model at all costs. - **Upskill:** The world is headed towards AI. It is here to stay. This has been my way of brushing up in this new form of computing challenge. - **Value:** I yearn to create value. I feel satisfaction and fulfillment in providing something meaningful for others. - **Fun:** It's just fun using and making models. It's also fun coming up with theories and realizing them in practice (training AI). I started my tuning venture back in mid-2024 when I wanted to improve its literary capabilities. I've come a long way since then and I have branched out and specialized. Foundational models today are optimized for non-creative uses, and I believe there is a place for AI in creativity and entertainment.

• Huihui-Qwen3.8-27B-abliterated-GGUF↗

  Weirdo333

  This is an uncensored version of Qwen/Qwen3.8-27B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens. The newly added **Huihui-Qwen3.8-27B-abliterated-Underdog-Saluki** series come from ConwayResearch/Underdog-Saluki-27B-1.0 and ukisai/Swift-1.5-Qwen3.8-27B-GSQ-RCO-GGUF. Only layers **22 to 52 (0-based indexing)** have been ablated, while the other layers remain unablated. It may come with a small disclaimer warning. Due to ConwayResearch/Underdog-Saluki-27B-1.0 not providing an imatrix file, we will attempt to perform ablation by mixing the GGUF weights of Swift-1.5 and ConwayResearch/Underdog-Saluki-27B-1.0.

• granite-3.3-8b-base↗

  ibm-granite

  Granite-3.3-8B-Base is a decoder-only language model with a 128K token context window. It improves upon Granite-3.1-8B-Base by adding support for Fill-in-the-Middle (FIM) using specialized tokens, enabling the model to generate content conditioned on both prefix and suffix. This makes it well-suited for code completion tasks. **Supported Languages:** English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. Users may finetune Granite 3.3 models for languages beyond these 12 languages. **Intended Use:** Prominent use cases of LLMs in text-to-text generation include summarization, text classification, extraction, question-answering, and other long-context tasks. All Granite Base models are able to handle these tasks as they were trained on a large amount of data from various domains. Moreover, they can serve as baseline to create specialized models for specific application scenarios.

• t5-small-txtsql↗

  NeuML

  T5 small fine-tuned to generate txtai SQL. This model takes natural language queries and builds txtai-compatible SQL statements. This model is an example of creating a custom query syntax that can be translated into SQL txtai can understand. Any query syntax can be created. This one supports English but a similar strategy can be deployed to support other languages. Natural language can be translated to functions, query clauses, column selection and more.

• MiniCPM-V-4.7-1B-abliterated-heretic-GGUF↗

  Abiray

  This repository provides quantized **GGUF** checkpoints for **MiniCPM-V 4.7 1B**, based on the refusal-abliterated weights created via **Heretic v1.4.0**. MiniCPM-V 4.7 1B is an ultra-efficient on-device multimodal large language model (MLLM) developed by OpenBMB. This version has been neutralized against standard refusal directions while retaining full multimodal vision and reasoning capabilities. The ablation was performed using **Heretic v1.4.0** to eliminate refusal bias while keeping Kullback–Leibler (KL) divergence near reference baseline:

• idefics-9b↗

  HuggingFaceM4

  IDEFICS (**I**mage-aware **D**ecoder **E**nhanced à la **F**lamingo with **I**nterleaved **C**ross-attention**S**) is an open-access reproduction of Flamingo, a closed-source visual language model developed by Deepmind. Like GPT-4, the multimodal model accepts arbitrary sequences of image and text inputs and produces text outputs. IDEFICS is built solely on publicly available data and models. The model can answer questions about images, describe visual contents, create stories grounded on multiple images, or simply behave as a pure language model without visual inputs. IDEFICS is on par with the original closed-source model on various image-text benchmarks, including visual question answering (open-ended and multiple choice), image captioning, and image classification when evaluated with in-context few-shot learning. It comes into two variants: a large 80 billion parameters version and a 9 billion parameters version.

• Qwen2.5-VL-7B-Instruct-abliterated↗

  huihui-ai

  --- license: apache-2.0 language: - en pipeline_tag: image-text-to-text tags: - multimodal - abliterated - uncensored library_name: transformers base_model: - Qwen/Qwen2.5-VL-7B-Instruct --- This is an uncensored version of Qwen/Qwen2.5-VL-7B-Instruct created with abliteration (see remove-refusals-with-transformers to know more about it). You can use huihui_ai/qwen2.5-vl-abliterated:7b directly,

• maxvit_small_tf_224.in1k↗

  timm

  An official MaxViT image classification model. Trained in tensorflow on ImageNet-1k by paper authors. Ported from official Tensorflow implementation (https://github.com/google-research/maxvit) to PyTorch by Ross Wightman. MaxxViT covers a number of related model architectures that share a common structure including: - CoAtNet - Combining MBConv (depthwise-separable) convolutional blocks in early stages with self-attention transformer blocks in later stages. - MaxViT - Uniform blocks across all stages, each containing a MBConv (depthwise-separable) convolution block followed by two self-attention blocks with different partitioning schemes (window followed by grid). - CoAtNeXt - A timm specific arch that uses ConvNeXt blocks in place of MBConv blocks in CoAtNet. All normalization layers are LayerNorm (no BatchNorm). - MaxxViT - A timm specific arch that uses ConvNeXt blocks in place of MBConv blocks in MaxViT. All normalization layers are LayerNorm (no BatchNorm). - MaxxViT-V2 - A MaxxViT variation that removes the window block attention leaving only ConvNeXt blocks and grid attention w/ more width to compensate. Aside from the major variants listed above, there are more subtle changes from model to model. Any model name with the string `rw` are `timm` specific configs w/ modelling adjustments made to favour PyTorch eager use. These were created while training initial reproductions of the models so there are variations. All models with the string `tf` are models exactly matching Tensorflow based models by the original paper authors with weights ported to PyTorch. This covers a number of MaxViT models. The official CoAtNet models were never released.

• unispeech-sat-base-plus-sv↗

  Microsoft

  The model was pretrained on 16kHz sampled speech audio with utterance and speaker contrastive loss. When using the model, make sure that your speech input is also sampled at 16kHz. Authors: Sanyuan Chen, Yu Wu, Chengyi Wang, Zhengyang Chen, Zhuo Chen, Shujie Liu, Jian Wu, Yao Qian, Furu Wei, Jinyu Li, Xiangzhan Yu **Abstract** *Self-supervised learning (SSL) is a long-standing goal for speech processing, since it utilizes large-scale unlabeled data and avoids extensive human labeling. Recent years witness great successes in applying self-supervised learning in speech recognition, while limited exploration was attempted in applying SSL for modeling speaker characteristics. In this paper, we aim to improve the existing SSL framework for speaker representation learning. Two methods are introduced for enhancing the unsupervised speaker information extraction. First, we apply the multi-task learning to the current SSL framework, where we integrate the utterance-wise contrastive loss with the SSL objective function. Second, for better speaker discrimination, we propose an utterance mixing strategy for data augmentation, where additional overlapped utterances are created unsupervisely and incorporate during training. We integrate the proposed methods into the HuBERT framework. Experiment results on SUPERB benchmark show that the proposed system achieves state-of-the-art performance in universal representation learning, especially for speaker identification oriented tasks. An ablation study is performed verifying the efficacy of each proposed method. Finally, we scale up training dataset to 94 thousand hours public audio data and achieve further performance improvement in all SUPERB tasks..*

• Huihui-Qwen3.6-27B-abliterated↗

  huihui-ai

  This is an uncensored version of Qwen/Qwen3.6-27B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.